© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8214
    Prev
    Next
    INDEX
    Explanations

    terms related to file management and extraction processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File compression or compressed files

    np_acts-logits-general · gemini-2.0-flash

    compression and zip files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.72
     Exactos
    -0.68
    AccessorTable
    -0.58
    ViewFeatures
    -0.57
    ckeys
    -0.56
     виправивши
    -0.54
    principalTable
    -0.54
    BrowserModule
    -0.54
    nestjs
    -0.53
    ViewImports
    -0.53
    POSITIVE LOGITS
     compression
    1.19
     compressed
    1.10
     Compression
    1.08
     compress
    1.03
    压缩
    1.01
    Compression
    1.00
    Zip
    0.98
     Zip
    0.97
    compression
    0.96
     zip
    0.96
    Activations Density 0.382%

    No Known Activations